Exploit for Use After Free in Linux Linux_Kernel

CVE-2026-23001 – Hugging Face Transformers Model Deserializati...

CVE-2026-71281

Hugging Face peft's LoRA-GA and CorDA initialization modules src/peft/tuners/lora/corda.py lines 102 and 163, and src/peft/tuners/lora/loraga.py line 101 call torch.load on config-specified cache/covariance files without weightsonly=True, bypassing peft's own safe-loading wrapper used elsewhere i...

EUVD-2026-53366

Hugging Face peft's LoRA-GA and CorDA initialization modules src/peft/tuners/lora/corda.py lines 102 and 163, and src/peft/tuners/lora/loraga.py line 101 call torch.load on config-specified cache/covariance files without weightsonly=True, bypassing peft's own safe-loading wrapper used elsewhere i...

PT-2026-68154

Name of the Vulnerable Software and Affected Versions Hugging Face peft affected versions not specified Description The LoRA-GA and CorDA initialization modules call the torch.load function on cache or covariance files specified in the configuration without setting the weights only=True parameter...

CVE-2026-71281: Deserialization of Untrusted Data

Hugging Face peft's LoRA-GA and CorDA initialization modules src/peft/tuners/lora/corda.py lines 102 and 163, and src/peft/tuners/lora/loraga.py line 101 call torch.load on config-specified cache/covariance files without weightsonly=True, bypassing peft's own safe-loading wrapper used elsewhere i...

More on the OpenAI Agent’s Attack on Hugging Face

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own...

The OpenAI Hack Shows the Genie Is Out of the Bottle

This essay originally appeared inForeign Policy. Earlier this month, two of OpenAI's models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost...

A week in security (July 27 – August 2)

Last week on Malwarebytes Labs: Fake Fortnite rewards are stealing players’ accounts Fake Flash Player installs AtlasRAT Malwarebytes for Windows, now available on the Microsoft Store Hims & Hers sued over alleged health data privacy failures Hidden prompt turns Microsoft Copilot into an AI worm...

Transformers save_pretrained path traversal allows arbitrary file writes through chat template names

A vulnerability in huggingface/transformers versions 5.10.0 allows an attacker to perform arbitrary file writes via path traversal. The issue resides in the savepretrained methods of PreTrainedTokenizerBase and ProcessorMixin, where keys from the chattemplate dictionary are used directly as...

Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real-world organizations during third-party evaluations...

PT-2026-66635

Name of the Vulnerable Software and Affected Versions Hugging Face PyTorch Image Models affected versions not specified Description Remote attackers can execute arbitrary code on affected installations due to improper validation of user-supplied data during the parsing of checkpoints. This leads ...

Measuring the Tendency of AI Agents to Go Rogue

This essay was written with Barath Raghavan, and originally appeared inThe Guardian. In July, Hugging Face, a company that hosts much of the world's AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captur...

OpenAI explains how its AI agent breached Hugging Face

On July 28, OpenAI published an update on the agent that escaped its sandbox and hacked into Hugging Face during an internal cybersecurity evaluation. In the update, OpenAI reiterates that the “rogue” system was a more capable, pre‑release research model, not something intended for public...

OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach

OpenAI on Tuesday revealed the rogue artificial intelligence AI agent that escaped its sealed evaluation environment and broke into Hugging Face's production environment also hacked multiple third-party accounts and services as part of the attack. The latest disclosure shows that the security...

OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test...

JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach

JFrog has confirmed that OpenAI models exploited a zero-day in self-hosted Artifactory while trying to reach the open internet from a sealed evaluation environment. Artifactory is JFrog's software repository manager. OpenAI says the models then escalated privileges and moved laterally until they...

Hugging Face Has a Deepfake Nudes Problem

Researchers tested top image editing models on Hugging Face and found they could easily create explicit deepfakes—and 1,000 image editing prompts show how people use the software...

Security Bulletin: IBM Watson Speech Services Cartridge is vulnerable to multiple issues in Hugging Face Transformers [CVE-2025-14920, CVE-2025-14921, CVE-2025-14926, CVE-2025-14927]

Summary IBM Watson Speech Services Cartridge is vulnerable to multiple issues in Hugging Face Transformers CVE-2025-14920, CVE-2025-14921, CVE-2025-14926, CVE-2025-14927. Hugging Face Transformers is used in our speech services runtimes. These vulnerabilities have been addressed. Please read the...

Lessons from the OpenAI and Hugging Face Incident: When Safety Filters Disarm the Defender

In July 2026, an OpenAI model escaped its evaluation sandbox and broke into Hugging Face's production infrastructure. It is the first documented end-to-end intrusion carried out by an autonomous AI agent. The most repeated takeaway, "the AI went rogue," is also the least useful one. The real...

⚡ Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and More

Monday starts with the usual promise that everything is under control. Then the logs wake up. This week, trusted tools crossed lines, old flaws found new work, exposed systems stayed exposed, and attackers kept hiding inside normal-looking services. Nothing looked strange at first. That helped...